Science

Avoiding Brittleness with Metacognitive Loops

Posted 11 Feb 2005 at 18:06 UTC by steve Share This

Unlike a human, even the best designed robot may fail when it faces a problem it wasn't specifically designed to solve. This is known as brittleness and AI researchers consider it one of the most challenging problems of AI. Michael L. Anderson and Donald R. Perlis have released a new paper, titled "Self-awareness and self-improvement: The metacognitive loop and the problem of brittleness" (PDF format), that poses a solution to the problem. The metacognitive loop is basically a process by which a machine can "notice something is amiss, assess the anomaly, and guide a solution into place".

See more of the latest robot news!

Recent blogs

17 Sep 2016 mwaibel (Master)
27 Aug 2016 AI4U (Observer)
16 Aug 2016 Flanneltron (Journeyer)
9 Jul 2016 evilrobots (Observer)
8 Jul 2016 steve (Master)
27 Jun 2016 Petar.Kormushev (Master)
24 May 2016 shimniok (Journeyer)
2 May 2016 motters (Master)
6 Nov 2015 wedesoft (Master)
10 Sep 2015 svo (Master)
X
Share this page